Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    safety, security, and guarantees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modeli
    0.43
    AccessToken
    0.41
    Equipment
    0.41
     disponível
    0.41
     newUser
    0.40
     modelu
    0.40
     الحاله
    0.39
    新技术
    0.39
    nergie
    0.39
    旂
    0.39
    POSITIVE LOGITS
     violations
    0.39
     monitored
    0.38
     livid
    0.37
     acted
    0.37
     minuto
    0.36
     sic
    0.36
     Λ
    0.36
     Aston
    0.36
     headed
    0.35
     ®
    0.35
    Act Density 0.001%

    No Known Activations